Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Date formats

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    她的
    -0.07
    ните
    -0.07
    _CTL
    -0.06
    phi
    -0.06
    Iterable
    -0.06
    ω
    -0.06
    _docs
    -0.06
    706
    -0.06
     sculpture
    -0.06
     Tumblr
    -0.06
    POSITIVE LOGITS
    лада
    0.06
     siden
    0.06
    profit
    0.06
     Orleans
    0.06
    리지
    0.06
    ادگی
    0.06
     vintage
    0.06
     Skeleton
    0.06
     techno
    0.06
     advent
    0.06
    Act Density 0.008%

    No Known Activations